Timeline for How can I minimize forecasting error in 100 probably correlated time series data streams with incomplete data from each one?
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 22, 2022 at 9:20 | history | edited | blackeneth | CC BY-SA 4.0 |
Revised based on posters comment
|
| Mar 21, 2022 at 21:02 | comment | added | FabianA | Thank you for your answer. One thought: "Fix the data that lumps two quarters together. Divide by 2, unless you justify a better method (say... Q1 has higher sales typically than Q2, so weight Q1 more)." - that seems to be the whole point of my question. That is: Can we, with the data we are given, extrapolate a better method using the fact that distributions might be correlated? If we had the data from 99 restaurants in perfect form and the summarized data from the final one, we could assume a probably perfect distribution. | |
| Mar 17, 2022 at 8:05 | history | answered | blackeneth | CC BY-SA 4.0 |